Revert "HUGGINGFACEHUB_API_TOKEN environment is change to HF_TOKEN (#… (#1521)

Revert this PR since the test is not triggered properly due to the false merge of a WIP CI PR, 44a689b0bf, which block the CI test.

This change will be submitted in another PR.
This commit is contained in:
chen, suyue
2025-02-11 18:36:12 +08:00
committed by GitHub
parent 47069ac70c
commit 81b02bb947
69 changed files with 113 additions and 263 deletions

View File

@@ -83,7 +83,7 @@ Default model is "Intel/neural-chat-7b-v3-3". Change "LLM_MODEL_ID" environment
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
```
When using gated models, you also need to provide [HuggingFace token](https://huggingface.co/docs/hub/security-tokens) to "HF_TOKEN" environment variable.
When using gated models, you also need to provide [HuggingFace token](https://huggingface.co/docs/hub/security-tokens) to "HUGGINGFACEHUB_API_TOKEN" environment variable.
### Setup Environment Variable
@@ -96,7 +96,7 @@ To set up environment variables for deploying Document Summarization services, f
export host_ip="External_Public_IP"
# Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
export no_proxy="Your_No_Proxy"
export HF_TOKEN="Your_Huggingface_API_Token"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
```
2. If you are in a proxy environment, also set the proxy-related environment variables:

View File

@@ -12,8 +12,7 @@ services:
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
host_ip: ${host_ip}
LLM_ENDPOINT_PORT: ${LLM_ENDPOINT_PORT}
healthcheck:
@@ -40,8 +39,7 @@ services:
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${LLM_ENDPOINT}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
MAX_INPUT_TOKENS: ${MAX_INPUT_TOKENS}
MAX_TOTAL_TOKENS: ${MAX_TOTAL_TOKENS}
LLM_MODEL_ID: ${LLM_MODEL_ID}

View File

@@ -75,7 +75,7 @@ Default model is "Intel/neural-chat-7b-v3-3". Change "LLM_MODEL_ID" environment
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
```
When using gated models, you also need to provide [HuggingFace token](https://huggingface.co/docs/hub/security-tokens) to "HF_TOKEN" environment variable.
When using gated models, you also need to provide [HuggingFace token](https://huggingface.co/docs/hub/security-tokens) to "HUGGINGFACEHUB_API_TOKEN" environment variable.
### Setup Environment Variable
@@ -88,7 +88,7 @@ To set up environment variables for deploying Document Summarization services, f
export host_ip="External_Public_IP"
# Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
export no_proxy="Your_No_Proxy"
export HF_TOKEN="Your_Huggingface_API_Token"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
```
2. If you are in a proxy environment, also set the proxy-related environment variables:

View File

@@ -13,7 +13,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HF_TOKEN}
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
HABANA_VISIBLE_DEVICES: all
@@ -48,7 +48,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
MAX_INPUT_TOKENS: ${MAX_INPUT_TOKENS}
MAX_TOTAL_TOKENS: ${MAX_TOTAL_TOKENS}
LLM_ENDPOINT: ${LLM_ENDPOINT}

View File

@@ -9,12 +9,6 @@ popd > /dev/null
export MAX_INPUT_TOKENS=1024
export MAX_TOTAL_TOKENS=2048
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export host_ip=$(hostname -I | awk '{print $1}')
export no_proxy="${no_proxy},${host_ip}"
export MEGA_SERVICE_HOST_IP=${host_ip}
export LLM_SERVICE_HOST_IP=${host_ip}